检索结果-内蒙古大学图书馆

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Zhang, Ying Zhu, Xiangyu Liu, Ajian Lin, Xun Wan, Jun Zhang, Jing Lei, Zhen Beihang University School of Computer Science and Engineering China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation China University of Chinese Academy of Sciences School of Artificial Intelligence China Macau University of Science and Technology School of Computer Science and Engineering China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation China

ISBN: (纸本)9798350364132

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model's parameters but also necessitates the provision of the image's modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image's modality to be known. Extensive experiments demonstrate CPL-CLIP's superiority over existing methods on several flexible-modal FAS benchmarks. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Framework for Temporal Cognitive Diagnosis in Online Learning Systems

引用

Journal of computer science & Technology 2023年第6期38卷 1203-1222页

作者：刘嘉聿汪飞马海平黄振亚刘淇陈恩红苏喻 School of Data Science University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Cognitive Intelligence Hefei 230088China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei 230026China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601China School of Computer Science and Artificial Intelligence Hefei Normal UniversityHefei 230061China

Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge *** existing studies rely on the assumption of static student states and ig-nore the dynamics of proficiency in the learning process,which makes them unsuitable for online learning *** this paper,we propose a unified temporal item response theory(UTIRT)framework,incorporating temporality and random-ness of proficiency evolving to get both accurate and interpretable diagnosis ***,we hypothesize that stu-dents'proficiency varies as a Wiener process and describe a probabilistic graphical model in UTIRT to consider temporali-ty and randomness ***,based on the relationship between student states and exercising answers,we hy-pothesize that the answering result at time k contributes most to inferring a student's proficiency at time k,which also re-flects the temporality aspect and enables us to get analytical maximization(M-step)in the expectation maximization(EM)algorithm when estimating model *** UTIRT is a framework containing unified training and inferenc-ing methods,and is general to cover several typical traditional models such as Item Response Theory(IRT),multidimen-sional IRT(MIRT),and temporal IRT(TIRT).Extensive experimental results on real-world datasets show the effective-ness of UTIRT and prove its superiority in leveraging temporality theoretically and practically over TIRT.

关键词： cognitive diagnosis probabilistic graphical model item response theory(IRT) stochastic process expectation maximization(EM)algorithm

来源：评论

学校读者我要写书评

暂无评论

Power Switching Based on Trajectory Planning and Sliding Mode Control for Solid Oxide Fuel Cell Systems

引用

Journal of Modern Power Systems and Clean Energy 2024年第6期12卷 1968-1979页

作者： Zhen Wang Guoqiang Liu Xingbo Liu Jie Wang Zhiyang Jin Xiaowei Fu Zhuo Wang Bing Jin Zhonghua Deng Xi Li Key Laboratory of Imaging Processing and Intelligent Control of Ministry of Education School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Research Institute of Huazhong University of Science and Technology in Shenzhen ShenzhenChina Hubei Huazhong Electric Power Technology Development Co. Ltd.WuhanChina School of Computer Science and Technology Wuhan University of Science and TechnologyWuhanChina School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhanChinaand he is also with the Wuhan Huamao Automation Co.Ltd.WuhanChina

To improve the safety of the solid oxide fuel cell(SOFC)systems and avoid the generation of large amounts of pollutants during power switching,this paper designs a power switching strategy based on trajectory planning and sliding mode control(TP-SMC).The design elements of the power switching strategy are proposed through simulation analysis at ***,based on the gas transmission delay time and the change of gas flow obtained from testing,trajectory planning(TP)is *** with other power switching strategies,it has been proven that the power switching strategy based on TP has significantly better control ***-thermore,considering the shortcomings and problems of TP in practical application,this paper introduces sliding mode control(SMC)on the basis of TP to improve the power switching *** final simulation results also prove that the TP-SMC can effectively suppress the impact of uncertainty in gas flow and gas transmission delay *** with TP,TP-SMC can ensure that under uncertain conditions,the SOFC system does not experience fuel starvation and temperature exceeding limit during power ***,the NOx emissions are also within the normal and acceptable *** paper can guide the power switching process of the actual SOFC sys-tems to avoid safety issues and excessive generation of NOx,which is very helpful for improving the performance and ser-vice lifeof the SOFCsystems.

关键词： Solid oxide fuel cell(SOFC)system power switching safety NOx emission trajectory planning sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Relation-wise transformer network and reinforcement learning for visual navigation

引用

Neural Computing and Applications 2024年第21期36卷 13205-13221页

作者： He, Yu Zhou, Kang School of Computer Science and Artificial Intelligence Huanghuai University Zhumadian463000 China Henan Key Laboratory of Smart Lighting Zhumadian463000 China Henan International Joint Laboratory of Behavior Optimization Control for Smart Robots Henan463000 China School of Computer Science City University of Hong Kong 999077 Hong Kong School of Computer Science Wuhan University Wuhan430072 China

The task of object goal navigation is to drive an embodied agent to find the location of a given target only using visual observation. The mapping from visual perception of observation determines the navigation actions. Heterogeneous relationships in the observation are the essential part of the scene graph, which can guide the agent to find the target more easily. In this work, we propose a novel Heterogeneous Zone Graph Visual Transformer formulation for graph representation and visual perception. It consists of two key ideas: (1) Heterogeneous Zone Graph (HZG) that explores the heterogeneous target-related zones graph and spatial information. It allows the agent to navigate efficiently. (2) Relation-wise Transformer Network (RTNet) that transforms the relationship between previously observed objects and navigation actions. RTNet extracts rich nodes and edges features as pays more attention to the target-related zone. We model self-attention on the node-to-node encoder and cross-attention on the edge-to-node decoder. We evaluate our methods on the AI2THOR dataset and show superior navigation performance. Code and datasets can be found inhttps://***/zhoukang12321/RTNet_VN_2023. © The Author(s) 2024.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

SeaCap: Multi-Sight Embedding and Alignment for One-Stage Image Captioner

引用

IEEE Transactions on Multimedia 2025年 27卷 3411-3425页

作者： Wang, Bo Zhang, Zhao Zhao, Mingbo Jin, Xiaojie Xu, Mingliang Wang, Meng Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Yunnan Key Laboratory of Software Engineering Yunan China Donghua University School of Computer Science and Engineering Shanghai201620 China ByteDance Culver CityCA90230 United States Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450001 China

Recent mainstream image captioning methods usually adopt two-stage captioners, i.e., calculating the object features of the given image by a pre-trained detector and then feeding them into a language model to generate the descriptive sentences. However, such a two-stage procedure will lead to a task-based information gap that decreases the performance of the captioners, because the object features learned from the detection task are suboptimal representations and cannot provide all the necessary information for subsequent sentence generation. Besides, the object features are usually represented by the last pooling features of the detector that lose the local details of images. In this paper, we propose a novel One-Stage Image Captioner using dynamic multi-sight embedding and alignment, called SeaCap, which directly transforms input images into descriptive sentences in one stage to eliminate the information gap. Specifically, to obtain rich features, we use the Swin Transformer to capture multi-level features, followed by a sights alignment module to alleviate the vision confusion, and then feed them into a novel dynamic multi-sight embedding module to exploit both the global structure and local texture of input images. To enhance the global modeling capacity of the visual encoder, we propose a new dual-dimensional refining module to non-locally model the interaction of the embedded features. As a result, SeaCap can obtain rich and useful information to improve the performance of the captioner. Extensive comparisons on the benchmark MS-COCO, Flickr8K and Flickr30 K datasets verified the superior performance of our method. © 1999-2012 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Network of Groupwise Separable Convolution and Vision Transformer for Hyperspectral Image Classification 3

A Lightweight Network of Groupwise Separable Convolution and...

引用

3rd International Conference on Optics and Machine Vision, ICOMV 2024

作者： Zhao, Zhuoyi Xu, Xiang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China The Artificial Intelligence and Computer Vision Laboratory University of Electronic Science and Technology of China Zhongshan Institute Zhongshan China

ISBN: (纸本)9781510680319

Hyperspectral image (HSI) data consists of images with numerous contiguous spectral bands and promotes the extensive applications in the field of remote sensing. Recent approaches based on Vision Transformer (ViT) have achieved remarkable performance in HSI classification tasks due to their ability to extract global spatial features and model long-range dependencies. However, ViT has complex network structure, training is challenging and lacks adequate consideration of local spatial and spectral receptive fields in hyperspectral data. To solve the problems above, we propose a lightweight network model known as the Groupwise Separable Convolution and Vision Transformer (GSCViT). Firstly, we introduce a parameter-free attention for spectral calibration (SC). Then, we meticulously design a novel convolutional approach named Groupwise Separable Convolution (GSC), which greatly reduce the number of convolutional kernel parameters and effectively capture local spatial-spectral information in HSI data. In addition, we employ Groupwise Separable Multi-Head Self-Attention (GSSA) to replace the traditional Multi-Head Self-Attention (MSA) in ViT, thus can simultaneously attend to local and global spatial features in HSI with lower computational burden. Experiments on two benchmark HSI datasets demonstrate that our GSCViT model achieves excellent accuracy with relatively small training samples and outperforms some existing HSI classification algorithms. © 2024 SPIE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Dynamic motion of quadrupedal robots on challenging terrain:a kinodynamic optimization approach

引用

Frontiers of Mechanical Engineering 2024年第3期19卷 23-40页

作者： Qi LI Lei DING Xin LUO Engineering Research Center of Hubei Province for Clothing Information Wuhan 430200China School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan 430200China State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China

The dynamic motion of quadrupedal robots on challenging terrain generally requires elaborate spatial–temporal kinodynamic motion planning and accurate control at higher refresh rate in comparison with regular ***,conventional quadrupedal robots usually generate relatively coarse planning and employ motion replanning or reactive strategies to handle terrain *** resultant complex and computation-intensive controller may lead to nonoptimal motions or the breaking of locomotion *** this paper,a kinodynamic optimization approach is *** generate long-horizon optimal predictions of the kinematic and dynamic behavior of the quadruped robot on challenging terrain,we formulate motion planning as an optimization problem;jointly treat the foot’s locations,contact forces,and torso motions as decision variables;combine smooth motion and minimal energy consumption as the objective function;and explicitly represent feasible foothold region and friction constraints based on terrain *** track the generated motions accurately and stably,we employ a whole-body controller to compute reference position and velocity commands,which are fed forward to joint controllers of the robot’s *** verify the effectiveness of the developed approach through simulation and on a physical quadruped robot *** show that the quadruped robot can successfully traverse a 30°slope and 43% of nominal leg length high step while maintaining the rhythm of dynamic trot gait.

关键词： quadrupedal robot kinodynamic planning nonlinear optimization challenging terrain whole-body control

来源：评论

学校读者我要写书评

暂无评论

Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation 38

Continuous Spatiotemporal Events Decoupling through Spike-ba...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zheng, Yajing Zhang, Jiyuan Yu, Zhaofei Huang, Tiejun State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Institute for Artificial Intelligence Peking University China

Numerous studies have demonstrated that the cognitive processes of the human brain can be modeled using the Bayes theorem for probabilistic inference of the external world. Spiking neural networks (SNNs), capable of performing Bayesian computation with greater physiological interpretability, offer a novel approach to distributed information processing in the cortex. However, applying these models to real-world scenarios to harness the advantages of brain-like computation remains a challenge. Recently, bio-inspired sensors with high dynamic range and ultra-high temporal resolution have been widely used in extreme vision scenarios. Event streams, generated by various types of motion, represent spatiotemporal data. Inferring motion targets from these streams without prior knowledge remains a difficult task. The Bayesian inference-based Expectation-Maximization (EM) framework has proven effective for motion segmentation in event streams, allowing for decoupling without prior information about the motion or its source. This work demonstrates that Bayesian computation based on spiking neural networks can decouple event streams of different motions. The Winner-Take-All (WTA) circuits in the constructed network implement an equivalent E-step, while Spike Timing Dependent Plasticity (STDP) achieves an equivalent optimization in the M-step. Through theoretical analysis and experiments, we show that STDP-based learning can maximize the contrast of warped events under mixed motion models. Experimental results show that the constructed spiking network can effectively segment the motion contained in event streams. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Topology Emulation Technology for the Space-Air-Ground Integrated Network

An Efficient Topology Emulation Technology for the Space-Air...

引用

2023 IEEE INFOCOM Conference on computer Communications Workshops, INFOCOM WKSHPS 2023

作者： Wang, Xiaofeng Shen, Taiqian Zhang, Yi Chen, Xinyu School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781665494274

The space-air-ground integrated network (SAGIN) is a comprehensive and complex network. Network emulation plays an important role in the validation and evaluation of SAGIN's new technologies. Aiming at the characteristics of heterogeneous nodes and the large-scale and dynamic topology of SAGIN, we propose an efficient topology emulation architecture for SAGIN, named SAGINHTE-Stack. To improve usability, scalability and efficiency, we propose three technologies: unified construction technology of the object model, static topology rapid deployment technology and topology dynamic synchronization technology. The experimental data show that the unified construction technology of the object model can complete the uni-fied model construction for various heterogeneous nodes. Static topology rapid deployment technology realizes the construction of the topology model at the millisecond level and completes the rapid deployment of the emulation topology. Topology dynamic synchronization technology realizes the parsing of the topology model change behavior and the synchronization of the topology model;moreover, topology dynamic synchronization technology completes the fast synchronization of the emulation topology. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Easier Ways to Prove Counting Hard: A Dichotomy for Generalized #SAT, Applied to Constraint Graphs 35

Easier Ways to Prove Counting Hard: A Dichotomy for Generali...

引用

35th International Symposium on Algorithms and Computation, ISAAC 2024

作者： Demaine, Erik D. Gomez, Timothy Stock, Frederick Brunner, Josh Diomidova, Jenny Hecher, Markus Zhou, Zixiang MIT Computer Science and Artificial Intelligence Laboratory CambridgeMA United States Miner School of Computer & Information Sciences University of Massachusetts LowellMA United States

ISBN: (纸本)9783959773546

To prove #P-hardness, a single-call reduction from #2SAT needs a clause gadget to have exactly the same number of solutions for all satisfying assignments - no matter how many and which literals satisfy the clause. In this paper, we relax this condition, making it easier to find #P-hardness reductions. Specifically, we introduce a framework called Generalized #SAT where each clause contributes a term to the total count of solutions based on a given function of the literals. For two-variable clauses (a natural generalization of #2SAT), we prove a dichotomy theorem characterizing when Generalized #SAT is in FP versus #P-complete. Equipped with these tools, we analyze the complexity of counting solutions to Constraint Graph Satisfiability (CGS), a framework previously used to prove NP-hardness (and PSPACE-hardness) of many puzzles and games. We prove CGS ASP-hard, meaning that there is a parsimonious reduction (with algorithmic bijection on solutions) from every NP search problem, which implies #P-completeness. Then we analyze CGS restricted to various subsets of features (vertex and edge types), and prove most of them either easy (in FP) or hard (#P-complete). Most of our results also apply to planar constraint graphs. CGS is thus a second powerful framework for proving problems #P-hard, with reductions requiring very few gadgets. © MIT Hardness Group, Josh Brunner, Erik D. Demaine, Jenny Diomidova, Timothy Gomez, Markus Hecher, Frederick Stock, and Zixiang Zhou.

关键词： Brinell Hardness

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：